Complex network analysis and machine learning for large-scale news-mining - Computer Science - PhD (Funded) Ref: 2662

About the award

The rise of the web and digital media has seen an explosion in the availability of big social data.  Computational analysis of online media using machine learning and natural language processing can uncover important relationships between people, organisations and events. These relationships can be aggregated into complex social networks that reveal patterns of interaction and influence.

This PhD project will apply natural language processing to large collections of text documents harvested from the web (e.g. social media, blogs, online news), in order to construct networks of interaction between people and organisations. These networks will then be analysed to explore how they change in response to external events, with the aim of developing methods to predict real-world events before they occur. For example, one application of such methods might be to derive a dynamic network of relationships between politicians based on online news articles – could this network be used to reveal patterns of power and influence, identify new political players, or to predict election outcomes?

You will have the opportunity to work on all aspects of the problem, from use of natural language processing and deep learning to extract entities and relations from large collections of unstructured text documents, to network construction based on these entities and relationships, to application of network statistics and machine learning to identify influential actors. Various datasets and networks are available to underpin this research, as well as a range of tools and software libraries. You will gain experience in a range of core techniques in data science and big data analysis, with a particular specialism in complex network analysis.

This fully funded 4-year project is co-sponsored by University of Exeter and a fast-growing data science company with offices in London and Bristol. The studentship will be based in the Computer Science department at University of Exeter and will interact with a vibrant interdisciplinary data science research community centred on the new Data Science Institute. Through the commercial sponsor, the studentship will benefit from hands-on training in advanced software tools and platforms, gaining invaluable exposure to commercial data science and experience in real-world big data analysis. The project offers excellent prospects for training and career progression.

Candidates should have a strong background in a quantitative discipline (e.g. maths, physics, computer science), with programming skills and experience of data analysis. Interested candidates are encouraged to contact Dr Hywel Williams ( for further information.


Application deadline:10th August 2017
Number of awards:1
Duration of award:per year
Contact: PGR Support office, tel: +44 1392

How to apply

To apply,please complete the online form. You will be asked to submit some personal details and upload a full CV, covering letter and details of two academic referees. Your covering letter should outline your academic interests, prior research experience and reasons for wishing to undertake this project.

You may also be asked to upload verified transcripts of your most academic qualification.

Interviews will be held in late August/ early September  2017. This studentship is available from September 2017.

If English is not your first language you will need to have achieved at least 6.5 in IELTS and no less than 6.0 in any section by the start of the project. Alternative tests may be acceptable (see